F score

Terms from Artificial Intelligence: humans at the heart of algorithms

The F score is an accuracy metric that combines precision and recall. It is defined as the harmonic mean of precision and recall, that is:
1/F = 0.5*( 1/precision + 1/recall )
. There are variants (Fβ that weight precision and recall differently. Also not to be confused with the F distribution used in statistical testing.

Used on page 176